
Safe Reinforcement Learning Using AdvantageBased Intervention
Many sequential decision problems involve finding a policy that maximize...
read it

Bellmanconsistent Pessimism for Offline Reinforcement Learning
The use of pessimism, when reasoning about datasets lacking exhaustive e...
read it

HeuristicGuided Reinforcement Learning
We provide a framework for accelerating reinforcement learning (RL) algo...
read it

Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
Policy optimization methods are popular reinforcement learning algorithm...
read it

RMP2: A Structured Composable Policy Class for Robot Learning
We consider the problem of learning motion policies for accelerationbas...
read it

RMPflow: A Geometric Framework for Generation of MultiTask Motion Policies
Generating robot motion for multiple tasks in dynamic environments is ch...
read it

Explaining Fast Improvement in Online Policy Optimization
Online policy optimization (OPO) views policy optimization for sequentia...
read it

Policy Improvement from Multiple Experts
Despite its promise, reinforcement learning's realworld adoption has be...
read it

Intra Orderpreserving Functions for Calibration of MultiClass Neural Networks
Predicting calibrated confidence scores for multiclass deep networks is...
read it

Continuous Online Learning and New Insights to Online Imitation Learning
Online learning is a powerful tool for analyzing iterative algorithms. H...
read it

A Reduction from Reinforcement Learning to NoRegret Online Learning
We present a reduction from reinforcement learning (RL) to noregret onl...
read it

Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping
RMPflow is a recently proposed policyfusion framework based on differen...
read it

Trajectorywise Control Variates for Variance Reduction in Policy Gradient Methods
Policy gradient methods have demonstrated success in reinforcement learn...
read it

Stable, Concurrent Controller Composition for MultiObjective Robotic Tasks
Robotic systems often need to consider multiple tasks concurrently. This...
read it

An Online Learning Approach to Model Predictive Control
Model predictive control (MPC) is a powerful technique for solving dynam...
read it

Online Learning with Continuous Variations: Dynamic Regret and Reductions
We study the dynamic regret of a new class of online learning problems, ...
read it

RMPflow: A Computational Graph for Automatic Motion Policy Generation
We develop a novel policy synthesis algorithm, RMPflow, based on geometr...
read it

Truncated Backpropagation for Bilevel Optimization
Bilevel optimization has been recently revisited for designing and analy...
read it

PredictorCorrector Policy Optimization
We present a predictorcorrector framework, called PicCoLO, that can tra...
read it

Orthogonally Decoupled Variational Gaussian Processes
Gaussian processes (GPs) provide a powerful nonparametric framework for...
read it

ModelBased Imitation Learning with Accelerated Convergence
Sample efficiency is critical in solving realworld reinforcement learni...
read it

Fast Policy Learning through Imitation and Reinforcement
Imitation learning (IL) consists of a set of tools that leverage expert ...
read it

Convergence of Value Aggregation for Imitation Learning
Value aggregation is a general framework for solving imitation learning ...
read it

Variational Inference for Gaussian Process Models with Linear Complexity
Largescale Gaussian process inference has long faced practical challeng...
read it
ChingAn Cheng
is this you? claim profile